An Automated Light Trap to Monitor Moths (Lepidoptera) Using Computer Vision-Based Tracking and Deep Learning

Abstract

Insect monitoring methods are typically very time-consuming and involve substantial investment in species identification following manual trapping in the field. Insect traps are often only serviced weekly, resulting in low temporal resolution of the monitoring data, which hampers the ecological interpretation. This paper presents a portable computer vision system capable of attracting and detecting live insects. More specifically, the paper proposes detection and classification of species by recording images of live individuals attracted to a light trap. An Automated Moth Trap (AMT) with multiple light sources and a camera was designed to attract and monitor live insects during twilight and night hours. A computer vision algorithm referred to as Moth Classification and Counting (MCC), based on deep learning analysis of the captured images, tracked and counted the number of insects and identified moth species. Observations over 48 nights resulted in the capture of more than 250,000 images with an average of 5675 images per night. A customized convolutional neural network was trained on 2000 labeled images of live moths represented by eight different classes, achieving a high validation F1-score of 0.93. The algorithm measured an average classification and tracking F1-score of 0.71 and a tracking detection rate of 0.79. Overall, the proposed computer vision system and algorithm showed promising results as a low-cost solution for non-destructive and automatic monitoring of moths.

Remote monitoring of Cydia pomonella adults among an assemblage of nontargets in sex pheromone‐kairomone‐baited smart traps

“…Second, the frequency of moth scales triggering a positive count could be reduced with the use of an adhesive that could minimize moth trails on the liner 33 . Third, the performance of the machine's identification algorithms could likely be improved by adjusting the saturation of the sticky liner background colour and narrowing the acceptable range of the automatic identification parameters 48,49 . However, accurate counting on liners with overlapping images due to crowding remains problematic 50 .…”

“… 33 Third, the performance of the machine's identification algorithms could likely be improved by adjusting the saturation of the sticky liner background colour and narrowing the acceptable range of the automatic identification parameters. 48 , 49 However, accurate counting on liners with overlapping images due to crowding remains problematic. 50 While weekly counts of codling moth are typically low, trap liners will need to be replaced throughout the season to avoid saturation and image integrity.…”

Presence and Biomass Information Extraction from Highly Uncertain Data of an Experimental Low-Range Insect Radar Setup

“…Many works confirm the effectiveness of trapping methods that belong to classical methods [6][7][8][9]. Among them, nowadays, automatic light camera traps are starting to play a central role due to technical progress [10][11][12][13]. A modern tendency to use the camera with light traps bridges trapping approaches with remote sensing methods of insect monitoring, where sky-oriented and unmanned aerial vehicleborne cameras are becoming more distinguishable due to the recent progress in robotics and computer vision [14][15][16].…”

Applying computer vision to digitised natural history collections for climate change research: temperature-size responses in British butterflies

“…CV is a rapidly developing field in which computers are trained to recognise, extract and measure information from digital images or video. While practical applications of CV have been made in several fields, such as object recognition/detection for medical purposes (e.g., tumor detection; Svoboda 2020) and ecologists are starting to use CV for biodiversity analyses in the field (Bjerge et al 2021), CV is only starting to be used for ecology and evolution research.…”